Separability of EEG signals recorded during right and left motor imagery using adaptive autoregressive parameters

Abstract

Electroencephalogram (EEG) recordings during right and left motor imagery can be used to move a cursor to a target on a computer screen. Such an EEG-based braincomputer interface (BCI) can provide a new communication channel to replace an impaired motor function. It can be used by, e.g., patients with amyotrophic lateral sclerosis (ALS) to develop a simple binary response in order to reply to specific questions. Four subjects participated in a series of on-line sessions with an EEG-based cursor control. The EEG was recorded from electrodes overlying sensory-motor areas during left and right motor imagery. The EEG signals were analyzed in subject-specific frequency bands and classified on-line by a neural network. The network output was used as a feedback signal. The on-line error (100%-perfect classification) was between 10.0 and 38.1%. In addition, the single-trial data were also analyzed off-line by using an adaptive autoregressive (AAR) model of order 6. With a linear discriminant analysis the estimated parameters for left and right motor imagery were separated. The error rate obtained varied between 5.8 and 32.8% and was, on average, better than the on-line results. By using the AAR-model for on-line classification an improvement in the error rate can be expected, however, with a classification delay around 1 s.

Linear and nonlinear methods for brain-computer interfaces

“…A second example is described by Garrett et al [27] who compare linear and nonlinear classifiers for the discrimination of EEG recorded while subjects perform one of five mental tasks. Previous work showed that a useful representation of multichannel windowed EEG signals consists of the parameters of an AR model of the data [1], [20]. One linear and two nonlinear classifiers were applied to EEG data represented as AR models.…”

“…1, it should be clear whether a given method was to be used in the feature extractor or the feature classifier. For instance, an autoregressive (AR) modeling method might be used in the process of extracting features from the electroencephalogram (EEG) signal (for example, see [20]). On the other hand, a nearest neighbor classifier method could be applied in the feature classification process (for example, see [15]).…”

Signal Processing and Classification Approaches for Brain-Computer Interface

“…AAR assume that the weights a i can vary over time. It seems that (AAR) parameters would give better results than (AR) parameters for motor imagery classification (Schlögl et al, 1997;Pfurtscheller et al, 1998), whereas they would give worse results for the classification of cognitive tasks such as mental computations, mental rotation of a geometric figure, etc. (Huan & Palaniappan, 2004a;Huan & Palaniappan, 2004b).…”

Independent Component Analysis for EEG Data Preprocessing - Algorithms Comparison

“…Succeeding parts of the BCI system are responsible for: measuring brain activity, preprocessing of the acquired signals, describing the signals by a few relevant features (feature extraction), selecting the most relevant features (feature selection), assigning a class to a set of selected features (classification), executing a command assigned to the chosen class and providing feedback to the user informing him about the mental state recognized by the BCI system. Although, all steps of the loop have to be carefully designed in order to build a successful BCI system, four of them play the major role: preprocessing [2][3][4], feature extraction [5][6], feature selection [7][8][9] and classification [10][11][12]. This paper deals with the first of these four main steps, it is with the preprocessing step.…”